Claim Missing Document
Check
Articles

Pengembangan Aplikasi Multimedia untuk Edukasi Sejarah pada Zaman Megalitikum Di Indonesia pada Platform Mobile Ihsan, Aminuddin; Yuniarti, Rezki; Ilyas, Ridwan
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2522

Abstract

This research developed a two-dimensional (2D) educational game themed on the history of the Megalithic Age in Indonesia for mobile platforms using the Rapid Prototyping method and Unity Engine. The aim was to provide interactive learning media that combines historical narratives with exploration-based game mechanics and puzzle solving. The development process included visual asset design, prototyping, and alpha and beta testing. Beta testing involved 20 respondents from junior high and high school levels, resulting in a satisfaction rate of 71.5% (Agree category) based on the Likert Scale, which indicates positive acceptance of the gameplay and educational content. The limitations of the study include the scope of historical material, which only covers the early Megalithic period, the limited number of respondents, and the difficulty level adjustment, which is not yet optimal for all age groups. Further development is recommended to expand the variety of missions, enrich historical content with the latest research references, and add analytical features to monitor user learning achievements.
Analisis Sentimen Terhadap Ulasan Aplikasi Deepseek AI Menggunakan Model Bidirectional LSTM dan IndoBert Mahendra, Lucky Syahroni; Herry Chrisnanto, Yulison; Yuniarti, Rezki
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2950

Abstract

Advancements in Natural Language Processing (NLP) technology have progressed rapidly, marked by the emergence of various Large Language Models (LLMs) such as ChatGPT, Gemini, and DeepSeek AI. One particularly popular model is DeepSeek AI due to its ability to understand and respond to natural language text more contextually. The increasing popularity of this application is accompanied by a growing number of user reviews, which serve as an important source of data for capturing their experiences and perceptions. This study aims to analyze user sentiment toward the DeepSeek AI application using a deep learning approach. Specifically, the research focuses on evaluating the performance of sentiment classification models in the context of Indonesian-language data, which is relatively limited and imbalanced. The dataset was collected from user reviews on the Google Play Store and categorized into three sentiment classes: positive, negative, and neutral. The method employed is a combination of IndoBERT and Bidirectional Long Short-Term Memory (BiLSTM). IndoBERT is used to generate contextual text representations in Indonesian, while BiLSTM is utilized to recognize sequential word patterns. Experimental results show that this hybrid model achieves an accuracy of 45%, with the highest F1-score of 0.66 in the positive class. Meanwhile, a macro-average F1-score of 0.33 and a ROC-AUC of 0.546 indicate that the model’s performance remains limited in distinguishing the three classes evenly. Nevertheless, the main contribution of this study lies in the development of a new dataset consisting of 1,774 Indonesian-language reviews related to LLM-based applications, which can be used for further research in the field of Natural Language Processing (NLP). The study also demonstrates the effectiveness of integrating IndoBERT and BiLSTM for sentiment analysis of Indonesian text with imbalanced data distribution.
Redesain UI/UX Website Sistem Informasi Gender Anak (SIGAB) Menggunakan Metode Design Thinking Fahmi Rizki Romdoni T; Puspita Nurul Sabrina; Rezki Yuniarti
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3100

Abstract

The need for transparency in gender data and child protection in Indonesia continues to increase along with the rise in cases of violence, gender inequality, and the demand for data-driven decision-making at the regional government level. The Gender and Child Information System (SIGAB) of Banten Province is an important instrument; however, the existing version still faces challenges such as complex navigation, less communicative data visualization, and low comprehensibility of the displayed indicators. This study aims to redesign the SIGAB interface using the Design Thinking method through five stages: empathize, define, ideate, prototype, and test. Data were collected through semi-structured interviews and questionnaires to identify user needs as the basis for solution formulation. The ideation stage produced concepts emphasizing simplified navigation, more informative data visualization, and the addition of insight text to facilitate indicator interpretation. The redesign resulted in four main pages—Main Dashboard, Gender, Children, and Sectoral—designed with an aesthetic and minimalist approach, clear information hierarchy, and thematic color palettes. Usability testing showed a significant improvement, with a Task Success Rate of 94% and an increase in the System Usability Scale (SUS) score from 58.7 to 85.5. These findings indicate that a Design Thinking–based redesign is able to enhance efficiency, comprehensibility, and user satisfaction in accessing gender and child data in Banten Province.